# Hierarchical Context Tagging for Utterance Rewriting

arXiv: https://arxiv.org/abs/2206.11218 · HTML: https://mlsanity.com/paper/2206.11218/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 22 Jun 2022.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Incorporating Copying Mechanism in Sequence-to-Sequence Learning](https://mlsanity.com/paper/1603.06393/) (2016)
- [Simple BERT Models for Relation Extraction and Semantic Role Labeling](https://mlsanity.com/paper/1904.05255/) (2019)
- [SParC: Cross-Domain Semantic Parsing in Context](https://mlsanity.com/paper/1906.02285/) (2019)
- [Multilingual Constituency Parsing with Self-Attention and Pre-Training](https://mlsanity.com/paper/1812.11760/) (2018)
- [Modeling Coverage for Neural Machine Translation](https://mlsanity.com/paper/1601.04811/) (2016)
- [Coreference Resolution as Query-based Span Prediction](https://mlsanity.com/paper/1911.01746/) (2019)
- [A Retrieve-and-Edit Framework for Predicting Structured Outputs](https://mlsanity.com/paper/1812.01194/) (2018)
- [Improving Multi-turn Dialogue Modelling with Utterance ReWriter](https://mlsanity.com/paper/1906.07004/) (2019)
- [Improving Coreference Resolution by Learning Entity-Level Distributed Representations](https://mlsanity.com/paper/1606.01323/) (2016)
- [AMR Parsing as Sequence-to-Graph Transduction](https://mlsanity.com/paper/1905.08704/) (2019)
- [Response Generation by Context-aware Prototype Editing](https://mlsanity.com/paper/1806.07042/) (2018)
- [Incomplete Utterance Rewriting as Semantic Segmentation](https://mlsanity.com/paper/2009.13166/) (2020)
- [Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation](https://mlsanity.com/paper/2106.08942/) (2021)
- [N-LTP: An Open-source Neural Language Technology Platform for Chinese](https://mlsanity.com/paper/2009.11616/) (2020)
- [SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration](https://mlsanity.com/paper/2008.01474/) (2020)
- [CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues](https://mlsanity.com/paper/2105.09914/) (2021)
- [Iterative Refinement for Machine Translation](https://mlsanity.com/paper/1610.06602/) (2016)
- [Robust Dialogue Utterance Rewriting as Sequence Tagging](https://mlsanity.com/paper/2012.14535/) (2020)

## Built on by (most cited first, 4 of 4)

- [DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection](https://mlsanity.com/paper/2210.11279/) (2022)
- [Incomplete Utterance Rewriting as Sequential Greedy Tagging](https://mlsanity.com/paper/2307.06337/) (2023)
- [Friend-training: Learning from Models of Different but Related Tasks](https://mlsanity.com/paper/2301.13683/) (2023)
- [Controllable Ancient Chinese Lyrics Generation Based on Phrase Prototype Retrieving](https://mlsanity.com/paper/2303.11005/) (2023)

## Abstract (arXiv)

Utterance rewriting aims to recover coreferences and omitted information from the latest turn of a multi-turn dialogue. Recently, methods that tag rather than linearly generate sequences have proven stronger in both in- and out-of-domain rewriting settings. This is due to a tagger's smaller search space as it can only copy tokens from the dialogue context. However, these methods may suffer from low coverage when phrases that must be added to a source utterance cannot be covered by a single context span. This can occur in languages like English that introduce tokens such as prepositions into the rewrite for grammaticality. We propose a hierarchical context tagger (HCT) that mitigates this issue by predicting slotted rules (e.g., "besides_") whose slots are later filled with context spans. HCT (i) tags the source string with token-level edit actions and slotted rules and (ii) fills in the resulting rule slots with spans from the dialogue context. This rule tagging allows HCT to add out-of-context tokens and multiple spans at once; we further cluster the rules to truncate the long tail of the rule distribution. Experiments on several benchmarks show that HCT can outperform state-of-the-art rewriting systems by ~2 BLEU points.